Abstract: Techniques are directed to a solution to the problem of underutilization of features offered by an application such as a browser by making such features more visible to a user by automatically (i.e., without user intervention), surfacing a user interface element configured to invoke a feature selected from a set of available features of the application in response to determining that the feature is relevant to the content displayed by the application. In some implementations, the set of available features is derived from a prespecified association between one or more resource identifiers (e.g., web page uniform resource locators (URLs)) and at least one feature.

Abstract: Systems and methods for a conversational assistant are disclosed. A method may include receiving a user query and determining that additional context is required. In response, environment content relevant to the query is identified and obtained. Identifying the content can involve generating an embedding of the query and comparing it to embeddings of resources previously accessed by the user, such as browser history or local files, to find resources that satisfy a similarity criterion. The user query and the obtained environment content are provided to the assistant. The assistant then provides a multi-modal output based on the combined information, where the output may include at least one action. Upon receiving the output, the action is performed. This enables the assistant to provide more relevant responses and perform tasks such as opening relevant webpages in an organized tab group, thereby streamlining the user's workflow.

Abstract: An application may receive a prompt from a user related to an input for a text field of digital content. An application may generate context data about the digital content. An application may provide the prompt and the context data to a generative language model. An application may receive a response generated by the generative language model and provide the response as a suggestion for the input for the text field.